Zhi Wei

May 23, 2024 | nature.com | Zhi Wei

CASTLE, a deep learning approach, extracts interpretable discrete representations from single-cell chromatin accessibility data, enabling accurate cell type identification, effective data integration, and quantitative insights into gene regulatory mechanisms.

May 23, 2024 | nature.com | Tian Tian |Xiang Lin |Zhi Wei

AbstractSpatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations.

Oct 19, 2023 | frontiersin.org | Miao Li |Zhi Wei |Tyler Hyungtaek |Debra Q. Y

IntroductionGlaucoma and cardiovascular diseases are among the top global concerns, given the increasing prevalence of these conditions and the associated burdens they impose (1, 2). Glaucoma is one of the leading causes of irreversible blindness (2), and CVD is one of the leading causes of mortality (1). Glaucoma is characterized by optic disc excavation and retinal nerve fiber layer (RNFL) thinning (3).